DSVNP uses global and local latent variables for improved neural process predictions.
problem Limited expressiveness of vanilla neural processes in capturing target-specific local variation.
method Introduces DSVNP combining global and local latent variables for prediction.
result Competitive prediction performance in multi-output regression and uncertainty estimation.
How to model distribution of sequential data, including but not limited to speech and human motions, is an important ongoing research problem. It has been demonstrated that model capacity can be significantly enhanced by introducing stochastic latent variables in the hidden states of recurrent neural networks. Simultan…
Enhances deep kernel learning with stochastic latent variables for better model regularization.
problem Weak model regularization in deep kernel learning, especially on small datasets.
method Introduces DLVKL model with stochastic latent variables, NSDE for expressive posterior, and hybrid prior.
result DLVKL-NSDE outperforms existing deep GPs on large datasets.
Particle MCMC involves using a particle filter within an MCMC algorithm. For inference of a model which involves an unobserved stochastic process, the standard implementation uses the particle filter to propose new values for the stochastic process, and MCMC moves to propose new values for the parameters. We show how p…
A new model encodes distances and topology in latent variables.
problem Modeling dissimilarity data with latent variables and invariances.
method Isometric Gaussian Process Latent Variable Model using Riemannian geometry and variational inference.
result The model can encode invariances in learned manifolds.
Method learns latent SDEs from high-dimensional time series.
problem Learning latent stochastic differential equations from time series data.
method Self-supervised learning with variational autoencoders and Euler-Maruyama approximation.
result Can recover SDE coefficients and latent variables up to isometry with infinite data.
Paper models graph edge dependencies using latent variables for community detection.
problem Graphs' edge dependencies not fully explained by community membership.
method Introduces auxiliary latent variables to model edge dependencies and analyzes conditions for exact recovery.
result Exact recovery possible by semidefinite programming down to maximum likelihood threshold.
New model captures state-dependent variability in partially observed systems.
problem Structured stochasticity not captured by constant-variance models.
method State-coupled stochastic volatility framework with particle expectation-maximization.
result Model consistently reduces recovery bias under partial observation.
Paper improves variational inference for complex models.
problem Improving statistical accuracy of variational inference in high-dimensional models.
method Developed a general framework for MFVI and proposed a partially grouped VI algorithm.
result Proposed algorithm works and outperforms vanilla MFVI in mixed membership stochastic blockmodel.
LSI enables joint learning of latent variables and generative models.
problem Joint optimization of latent variables and generative models.
method Developed a principled ELBO objective in continuous time for joint learning.
result LSI learns effective latent representations and generative transformations.
GFlowNet-EM learns complex latent variable models with discrete structures.
problem Challenges in modeling posteriors over discrete compositional latents with expectation-maximization.
method Uses GFlowNets to learn stochastic policies for sampling from complex posterior distributions.
result GFlowNet-EM enables training expressive LVMs with discrete compositional latents.
A scalable GPLVM model using stochastic variational inference.
problem Scalable inference for Gaussian process latent variable models.
method Doubly stochastic formulation of Bayesian GPLVM with minibatch training.
result High-fidelity reconstructions in the presence of missing data.
New method improves uncertainty quantification in latent variable models.
problem Uncertainty quantification in latent variable models with SGLD-Gibbs.
method Statistical scaling limit theory for SGLD-Gibbs, proposing hyperparameter tuning.
result Explicit guidance on hyperparameter tuning for SGLD-Gibbs ensures meaningful uncertainty quantification.
Proposes flexible auto-encoders for varying data dimensions.
problem Fixed latent dimensions limit data flexibility.
method Stochastic bottleneck with weighted dropouts.
result Seamless variable dimensionality reduction with high performance.
Two-Timescale EM Methods improve EM for nonconvex models.
problem Nonconvex latent variable models are challenging for EM.
method Two-stage stochastic updates to handle nonconvex optimization.
result Global convergence for nonconvex objective functions.
Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We unify successful ideas from recently pr…
New method uses joint stochastic approximation to improve learning of discrete latent models.
problem Challenges in learning discrete latent variable models, especially with inference model gradients and log-likelihood optimization.
method Proposes a new method based on stochastic approximation theory that directly maximizes the target log-likelihood and minimizes the posterior-inference model divergence.
result Consistently outperforms recent competitive algorithms in generative modeling and structured prediction tasks.
This paper benchmarks speech LVMs against deterministic models and adapts a video model to speech.
problem Speech generation models are inferior to deterministic models.
method Developed a speech benchmark of LVMs and compared them against deterministic models.
result The Clockwork VAE outperforms previous LVMs and reduces the gap to deterministic models.
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have limited expressive power due to the Gaussian assumption of latent variables. In t…
New method learns latent energy models using particle algorithms.
problem Learning latent variable models with energy priors.
method Continuous-time SDEs for MMLE, particle-based discretization.
result Practical algorithm converges to solve MMLE problem.
New method selects features for sequential decision making.
problem Dynamic feature selection for instance-wise decisions.
method Latent variable model trained in a supervised manner; reasoning across stochastic latent space.
result Outperforms existing methods on various datasets.
Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We describe and study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. First, we show how such a decomposition ar…
Method learns model for unknown stochastic system from data.
problem Modeling unknown stochastic dynamical systems.
method Autoencoder approach using deep neural networks (DNNs).
result Decoder serves as a predictive model for unknown stochastic systems.
Generative models learn latent process to match target distributions.
problem Training flow-matching models with auxiliary stochastic dynamics.
method Introduces latent process generator matching, treating generative state as a deterministic image of a Markov process.
result Learn generator of a stochastic process with same marginal distributions.
A new method reduces variance in training discrete latent variable models.
problem High variance in stochastic gradient estimators for discrete latent variable models.
method Double control variates for score function estimators using Taylor expansions.
result Our method can have lower variance compared to other estimators.
With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their performance in terms of test likelihood and quality of generated samples has been surpassed by autoregressive models without stochastic units. Fu…
A scalable MOGP model with stochastic variational inference for many outputs.
problem Efficiently modeling data from multiple sources with many outputs.
method Stochastic variational inference for Latent Variable MOGP (LV-MOGP).
result Computational complexity per iteration is independent of the number of outputs.
Stochastic neural networks with infinite width become deterministic, reducing training variance.
problem Understanding how stochasticity in neural networks affects learning and regularization.
method Theoretical analysis of stochastic neural networks with infinite width.
result As the width of an optimized stochastic neural network increases, its predictive variance on the training set decreases to zero.
With latent variables, stochastic recurrent models have achieved state-of-the-art performance in modeling sound-wave sequence. However, opposite results are also observed in other domains, where standard recurrent networks often outperform stochastic models. To better understand this discrepancy, we re-examine the role…
Paper detects hierarchical changes in latent variable models from data streams.
problem Detecting changes at three levels: data distribution, latent variables, and number of latent variables.
method Information-theoretic framework using MDL and DNML for change detection.
result Effective in detecting changes with good interpretability.
Improved exploration in RL with latent state marginalization.
problem Complexity of deep probabilistic models limits their practical use in reinforcement learning.
method Adopting latent variable policies within the MaxEnt framework, with low-cost marginalization of latent states.
result Effective marginalization leads to better exploration and more robust training.
Model infers latent variables in sparse coding models using Langevin dynamics.
problem Sampling posterior distribution in sparse coding models.
method Langevin dynamics for inference and simultaneous learning of parameters.
result Langevin dynamics efficiently sample from 'L0 sparse' posterior distribution.
New JSA autoencoders tackle discrete latent variable models for semi-supervised learning.
problem Handling discrete observations and latent codes in deep generative models.
method Joint-stochastic-approximation (JSA) autoencoders that directly maximize data log-likelihood and minimize KL divergence.
result JSA autoencoders achieve comparable performance to continuous latent space models in semi-supervised tasks.
A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing…
Flexible model tackles high-dimensional, missing data, and stochastic processes.
problem High-dimensional longitudinal data with structured missingness and unknown measurement time points.
method Latent variable model using Gaussian processes and variational autoencoder.
result Competitive performance on simulated and real datasets.
New method for LVEBMs using saddle-point optimization and Langevin updates.
problem Expressive generative modeling of latent variables with hidden structure.
method Reformulate LVEBM training as a saddle problem, using Langevin updates and gradient flows.
result Proves existence and convergence of the algorithm under standard assumptions, with improved ELBO bounds.
Model detects epileptic seizures in EEG with high sensitivity.
problem Detecting epileptic seizures in EEG signals.
method Time-series scale mixture model with hidden Markov structure.
result Model outperformed baselines in seizure detection.
Bayesian Neural Networks with Latent Variables (BNN+LVs) capture predictive uncertainty by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise variable). In this work, we first show that BNN+LV suffers from a serious form of non-identifiability…
New algorithm improves latent variable model estimation.
problem Estimating parameters in latent variable models.
method Jarzynski-adjusted Langevin algorithm (JALA) for SMC methods.
result JALA-EM provides maximum marginal likelihood estimate.
Neural networks learn faster with correlated latent variables.
problem Efficiently learning from higher-order correlations in neural networks.
method Analytical derivation and simulations of two-layer neural networks.
result Correlations between latent variables speed up learning from higher-order correlations.
Enhances neural processes for better context handling.
problem Real-world context sets are complex, requiring richer prior distributions.
method Introduces a graphical model for a richer prior on latent variables, enabling end-to-end optimization.
result Improves function modeling and test-time robustness with mixture and Student-t assumptions.
Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to inherent parallelism. However, currently there remains a performance gap to mor…
Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evidence is typically intractable, thus a common approximation is to maximize the evidence lower bound (ELBO) instead. However, maximum likeliho…
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.
It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently …
While stochastic variational inference is relatively well known for scaling inference in Bayesian probabilistic models, related methods also offer ways to circumnavigate the approximation of analytically intractable expectations. The key challenge in either setting is controlling the variance of gradient estimates: rec…
This paper tackles causal representation learning with linear and general transformations.
problem Identify and recover latent causal variables and graphs under unknown transformations.
method Score-based algorithms that use gradients of log-density functions for identifiability and achievability.
result Two stochastic hard interventions per node are sufficient for identifiability of general transformations.
High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which im…